Quick Start Guide

This guide walks you through making your first FinBrain API calls. By the end, you’ll know how to retrieve AI price predictions, insider trading data, and sentiment scores.

Prerequisites

• A FinBrain API key (sign up here)
• Python 3.7+ or any HTTP client

Step 1: Set Up Authentication

All FinBrain API v2 endpoints use Bearer token authentication. Include your API key in the Authorization header of every request:

Authorization: Bearer YOUR_API_KEY

Step 2: Set Up Your Environment

import requests

API_KEY = "YOUR_API_KEY"
headers = {"Authorization": f"Bearer {API_KEY}"}

Step 3: Fetch Data

Get AI Price Predictions

Retrieve deep learning price forecasts for any ticker:

Python SDK

from finbrain import FinBrainClient

fb = FinBrainClient(api_key="YOUR_API_KEY")

# Get daily predictions for Apple as DataFrame
df = fb.predictions.ticker("AAPL", prediction_type="daily",
                           as_dataframe=True)
print(df)
#                   mid    lower    upper
# date
# 2025-11-04     201.33   197.21   205.45
# 2025-11-05     202.77   196.92   208.61

Python (requests)

import requests

API_KEY = "YOUR_API_KEY"
headers = {"Authorization": f"Bearer {API_KEY}"}

response = requests.get(
    "https://api.finbrain.tech/v2/predictions/daily/AAPL",
    headers=headers
)
data = response.json()
print(data)

Sample JSON Output:

{
  "success": true,
  "data": {
    "ticker": "AAPL",
    "name": "Apple Inc.",
    "predictions": [
      { "date": "2025-11-04", "mid": 201.33, "lower": 197.21, "upper": 205.45 },
      { "date": "2025-11-05", "mid": 202.77, "lower": 196.92, "upper": 208.61 },
      { "date": "2025-11-06", "mid": 203.99, "lower": 196.90, "upper": 211.08 }
    ],
    "metadata": {
      "expectedShortTerm": 0.22,
      "expectedMidTerm": 0.58,
      "expectedLongTerm": 0.25,
      "type": "daily",
      "lastUpdated": "2025-11-01T23:24:18.371Z"
    }
  },
  "meta": {
    "timestamp": "2025-11-02T10:15:30.000Z"
  }
}

JavaScript

const response = await fetch(
  "https://api.finbrain.tech/v2/predictions/daily/AAPL",
  { headers: { "Authorization": "Bearer YOUR_API_KEY" } }
);
const data = await response.json();
console.log(data);

cURL

curl -H "Authorization: Bearer YOUR_API_KEY" \
  "https://api.finbrain.tech/v2/predictions/daily/AAPL"

Get Insider Trading Data

Track executive purchases and sales from SEC Form 4 filings:

Python SDK

from finbrain import FinBrainClient

fb = FinBrainClient(api_key="YOUR_API_KEY")

# Get insider transactions for Tesla as DataFrame
df = fb.insider_transactions.ticker("TSLA", as_dataframe=True)
print(df.head())

Python (requests)

import requests

API_KEY = "YOUR_API_KEY"
headers = {"Authorization": f"Bearer {API_KEY}"}

response = requests.get(
    "https://api.finbrain.tech/v2/insider-trading/TSLA",
    headers=headers
)
data = response.json()
print(data)

Sample JSON Output:

{
  "success": true,
  "data": {
    "ticker": "TSLA",
    "name": "Tesla Inc.",
    "transactions": [
      {
        "date": "2025-01-10",
        "insider": "Elon Musk",
        "relationship": "CEO",
        "transactionType": "Sale",
        "pricePerShare": 245.50,
        "shares": 50000,
        "totalValue": 12275000,
        "sharesOwned": 715000000,
        "filingUrl": "https://sec.gov/..."
      }
    ]
  },
  "meta": {
    "timestamp": "2025-01-12T08:30:00.000Z"
  }
}

JavaScript

const response = await fetch(
  "https://api.finbrain.tech/v2/insider-trading/TSLA",
  { headers: { "Authorization": "Bearer YOUR_API_KEY" } }
);
const data = await response.json();
console.log(data);

cURL

curl -H "Authorization: Bearer YOUR_API_KEY" \
  "https://api.finbrain.tech/v2/insider-trading/TSLA"

Get Sentiment Scores

Access AI-powered sentiment analysis from financial news:

Python SDK

from finbrain import FinBrainClient

fb = FinBrainClient(api_key="YOUR_API_KEY")

# Get sentiment for Microsoft as DataFrame
df = fb.sentiments.ticker("MSFT", as_dataframe=True)
print(df.tail())

Python (requests)

import requests

API_KEY = "YOUR_API_KEY"
headers = {"Authorization": f"Bearer {API_KEY}"}

response = requests.get(
    "https://api.finbrain.tech/v2/sentiment/MSFT",
    headers=headers
)
data = response.json()
print(data)

Sample JSON Output:

{
  "success": true,
  "data": {
    "ticker": "MSFT",
    "name": "Microsoft Corporation",
    "sentiments": [
      { "date": "2025-01-15", "score": 0.72 },
      { "date": "2025-01-14", "score": 0.68 },
      { "date": "2025-01-13", "score": 0.65 },
      { "date": "2025-01-12", "score": 0.70 },
      { "date": "2025-01-11", "score": 0.63 }
    ]
  },
  "meta": {
    "timestamp": "2025-01-16T06:00:00.000Z"
  }
}

JavaScript

const response = await fetch(
  "https://api.finbrain.tech/v2/sentiment/MSFT",
  { headers: { "Authorization": "Bearer YOUR_API_KEY" } }
);
const data = await response.json();
console.log(data);

cURL

curl -H "Authorization: Bearer YOUR_API_KEY" \
  "https://api.finbrain.tech/v2/sentiment/MSFT"

Get Congressional Trades

Monitor US House Representatives trading activity:

Python SDK

from finbrain import FinBrainClient

fb = FinBrainClient(api_key="YOUR_API_KEY")

# Get House trades for NVIDIA as DataFrame
df = fb.house_trades.ticker("NVDA", as_dataframe=True)
print(df.head())

Python (requests)

import requests

API_KEY = "YOUR_API_KEY"
headers = {"Authorization": f"Bearer {API_KEY}"}

response = requests.get(
    "https://api.finbrain.tech/v2/congress/house/NVDA",
    headers=headers
)
data = response.json()
print(data)

Sample JSON Output:

{
  "success": true,
  "data": {
    "ticker": "NVDA",
    "name": "NVIDIA Corporation",
    "trades": [
      {
        "date": "2025-01-08",
        "politician": "Nancy Pelosi",
        "transactionType": "Purchase",
        "amount": "$1,000,001 - $5,000,000",
        "chamber": "house"
      }
    ]
  },
  "meta": {
    "timestamp": "2025-01-10T12:00:00.000Z"
  }
}

JavaScript

const response = await fetch(
  "https://api.finbrain.tech/v2/congress/house/NVDA",
  { headers: { "Authorization": "Bearer YOUR_API_KEY" } }
);
const data = await response.json();
console.log(data);

cURL

curl -H "Authorization: Bearer YOUR_API_KEY" \
  "https://api.finbrain.tech/v2/congress/house/NVDA"

Step 4: Filter by Date Range

Most endpoints support date filtering:

Python SDK

from finbrain import FinBrainClient

fb = FinBrainClient(api_key="YOUR_API_KEY")

df = fb.sentiments.ticker(
    "AAPL",
    date_from="2025-01-01",
    date_to="2025-01-31",
    as_dataframe=True
)
print(df)

Python (requests)

import requests

API_KEY = "YOUR_API_KEY"
headers = {"Authorization": f"Bearer {API_KEY}"}

response = requests.get(
    "https://api.finbrain.tech/v2/sentiment/AAPL",
    headers=headers,
    params={"startDate": "2025-01-01", "endDate": "2025-01-31"}
)
data = response.json()
print(data)

cURL

curl -H "Authorization: Bearer YOUR_API_KEY" \
  "https://api.finbrain.tech/v2/sentiment/AAPL?startDate=2025-01-01&endDate=2025-01-31"

Complete Example

Here’s a complete script that fetches multiple datasets for a ticker:

Python SDK

from finbrain import FinBrainClient

fb = FinBrainClient(api_key="YOUR_API_KEY")

ticker = "AAPL"
print(f"Analyzing {ticker}...\n")

# AI Predictions
predictions_df = fb.predictions.ticker(ticker, as_dataframe=True)
print("AI Predictions:")
print(predictions_df.head())

# Insider Transactions
insiders_df = fb.insider_transactions.ticker(ticker, as_dataframe=True)
print("\nInsider Transactions:")
print(insiders_df.head())

# Sentiment
sentiment_df = fb.sentiments.ticker(ticker, as_dataframe=True)
print("\nSentiment Scores:")
print(sentiment_df.tail())

# Congressional Trades
trades_df = fb.house_trades.ticker(ticker, as_dataframe=True)
print("\nCongressional Trades:")
print(trades_df.head())

Python (requests)

import requests

API_KEY = "YOUR_API_KEY"
BASE_URL = "https://api.finbrain.tech/v2"
headers = {"Authorization": f"Bearer {API_KEY}"}

ticker = "AAPL"
print(f"Analyzing {ticker}...\n")

# AI Predictions
resp = requests.get(f"{BASE_URL}/predictions/daily/{ticker}", headers=headers)
predictions = resp.json()
if predictions["success"]:
    for p in predictions["data"]["predictions"][:3]:
        print(f"  {p['date']}: mid={p['mid']}, range=[{p['lower']}, {p['upper']}]")

# Insider Transactions
resp = requests.get(f"{BASE_URL}/insider-trading/{ticker}", headers=headers)
insiders = resp.json()
if insiders["success"]:
    print("\nInsider Transactions:")
    for txn in insiders["data"]["transactions"][:3]:
        print(f"  {txn['date']}: {txn['insider']} - {txn['transactionType']} "
              f"{txn['shares']} shares @ ${txn['pricePerShare']}")

# Sentiment
resp = requests.get(f"{BASE_URL}/sentiment/{ticker}", headers=headers)
sentiment = resp.json()
if sentiment["success"]:
    print("\nSentiment Scores:")
    for s in sentiment["data"]["sentiments"][:5]:
        print(f"  {s['date']}: {s['score']}")

# Congressional Trades
resp = requests.get(f"{BASE_URL}/congress/house/{ticker}", headers=headers)
congress = resp.json()
if congress["success"]:
    print("\nCongressional Trades:")
    for t in congress["data"]["trades"][:3]:
        print(f"  {t['date']}: {t['politician']} - {t['transactionType']} ({t['amount']})")

Next Steps

Now that you’ve made your first API calls, explore more:

• Datasets - Detailed dataset documentation
• API Reference - Complete endpoint reference
• Python SDK - Full SDK documentation